© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8974
    Prev
    Next
    INDEX
    Explanations

    inconsistent, but the neuron frequently activates on words relating to conflict and resolution, as well as some technological information.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onAttach
    -0.56
    aarrggbb
    -0.52
    IGraphics
    -0.51
    Jeografia
    -0.47
     EST
    -0.46
    туга
    -0.46
    =!
    -0.46
    jsdelivr
    -0.46
    UnknownFields
    -0.45
    . 
    -0.45
    POSITIVE LOGITS
    fraid
    0.93
    owners
    0.84
    neath
    0.84
    theless
    0.83
    tened
    0.81
    drawal
    0.80
    gether
    0.79
    heritance
    0.79
    imed
    0.76
    xious
    0.76
    Activations Density 9.148%

    No Known Activations